Story Prompt
A real, playable collaborative-story game session with genuine twist and wrap-up logic
A hand-curated scavenger-hunt & treasure-hunt design reference — clue formats, occasion fit, and a genuine pacing planner
Unify Dynamics LLC
Real questions, and the tools your agent calls to answer them.
format_infoclue_writing_tiphunt_plannerterm_glossaryvenue_considerationfind_format_for_occasioncategory_listbeginner_tipsScavenger is a fully local, hand-curated scavenger-hunt & treasure-hunt design reference. format_info explains one clue-writing format in depth (riddle-based, location-based, photo-based, QR-code-based, cipher/code-breaking, trivia-question, physical-challenge, item-checklist, word-puzzle, jigsaw/fragment, audio, video, map-based, numeric-puzzle, story/narrative-embedded, sensory, hybrid/mixed) with how it works, materials, tech requirements, pros/cons and an original example clue. clue_writing_tip gives craft-level writing guidance, common mistakes, and a strong-vs-weak example for a named format. hunt_planner is genuine, live-computed pacing math: given duration, team count and difficulty, it returns a recommended clue count, an easy/medium/hard difficulty mix that ramps harder toward the finish, estimated timing, a hint threshold, and staggered-start guidance for multiple teams. find_format_for_occasion suggests formats and design choices for a stated occasion (wedding, kids' birthday, corporate team-building, and more). venue_consideration covers planning, safety, permission and accessibility notes for indoor and outdoor venue types. term_glossary defines hunt-design vocabulary; category_list lists every clue-format category; beginner_tips gives a ranked shortlist for first-time hunt planners. Keyless; fully local; zero upstream calls; nothing stored.
Sources: Hand-curated original scavenger-hunt and treasure-hunt design guidance and live-computed pacing math; fully local, zero upstream calls
The publisher, Unify Dynamics LLC, states that tool inputs are processed in memory and not retained.
8 tools, grouped by job. Every one is read-only or compute-only.
https://scavenger.connectorbay.com/mcpThree ways in, the same 8 tools.
https://scavenger.connectorbay.com/mcpPOST https://scavenger.connectorbay.com/v1/tools/<tool>https://connectorbay.com/openai/scavenger.jsonhttps://connectorbay.com/v1/chat/completions · how it worksScavenger is a fully local, hand-curated scavenger-hunt & treasure-hunt design reference. It is a hosted MCP server with 8 tools such as Format info, Clue writing tip, Hunt planner, Term glossary, Venue consideration, Find format for occasion, published by Unify Dynamics LLC. It is independent and not affiliated with Scavenger.
Add the MCP endpoint https://scavenger.connectorbay.com/mcp to your client's MCP, connector or integration settings (streamable HTTP, no OAuth). For REST, POST JSON to https://scavenger.connectorbay.com/v1/tools/<tool>; the OpenAPI description is at /openapi.json. For OpenAI function calling, load https://connectorbay.com/openai/scavenger.json.
No. The connector needs no sign-in and no key. An optional Pro key only raises rate limits.
Yes. Every tool reads or computes. Nothing is created, changed, sent, paid or deleted in your account.
Yes. It is free to use within the published rate limits; an optional Pro key raises them. There is no account to create.
A real, playable collaborative-story game session with genuine twist and wrap-up logic
A real, playable family dare game session with 110+ original, family-safe dares
A real, playable conversation-starter game session that genuinely deepens over time
A real, playable Would You Rather game session with 110+ original dilemmas
A playable toggle-puzzle engine with a real GF(2) minimum-press solver
A playable cage-arithmetic (calcudoku) engine with uniquely-solvable generation
https://scavenger.connectorbay.com/mcpPOST https://scavenger.connectorbay.com/v1/tools/{tool_name}, described by the OpenAPI 3.1 spec at https://scavenger.connectorbay.com/openapi.jsonAuthorization: Bearer <key> raises rate limits.https://scavenger.connectorbay.com/health · Tool schemas: https://scavenger.connectorbay.com/tools.jsonA hand-curated scavenger-hunt & treasure-hunt design reference — clue formats, occasion fit, and a genuine pacing planner.
Scavenger is a fully local, hand-curated scavenger-hunt & treasure-hunt design reference. format_info explains one clue-writing format in depth (riddle-based, location-based, photo-based, QR-code-based, cipher/code-breaking, trivia-question, physical-challenge, item-checklist, word-puzzle, jigsaw/fragment, audio, video, map-based, numeric-puzzle, story/narrative-embedded, sensory, hybrid/mixed) with how it works, materials, tech requirements, pros/cons and an original example clue. clue_writing_tip gives craft-level writing guidance, common mistakes, and a strong-vs-weak example for a named format. hunt_planner is genuine, live-computed pacing math: given duration, team count and difficulty, it returns a recommended clue count, an easy/medium/hard difficulty mix that ramps harder toward the finish, estimated timing, a hint threshold, and staggered-start guidance for multiple teams. find_format_for_occasion suggests formats and design choices for a stated occasion (wedding, kids' birthday, corporate team-building, and more). venue_consideration covers planning, safety, permission and accessibility notes for indoor and outdoor venue types. term_glossary defines hunt-design vocabulary; category_list lists every clue-format category; beginner_tips gives a ranked shortlist for first-time hunt planners. Keyless; fully local; zero upstream calls; nothing stored.
Not an official product of, or affiliated with, any brand, league, publisher, or organization it may factually mention. Scavenger is a hand-curated reference and design tool, not a substitute for an official rulebook, certified instruction, or professional advice. Fully local, zero upstream calls, nothing stored.
format_info — Full detail for one clue-writing format: category, how it works, difficulty to write and to solve, best occasions, materials needed, whether tech is required, pros and cons, and an original example clue. Use for "how does a photo-based clue work", "what do I need for a QR-code hunt station". Args: name.
clue_writing_tip — Craft-level guidance for writing a good clue of a named format: specific writing tips, common mistakes to avoid, and a strong-vs-weak example. Use for "tips for writing a good riddle clue", "what mistakes should I avoid with a cipher clue", "how do I write a good photo clue". Args: clue_type.
hunt_planner — Genuine clue-count and pacing math for a scavenger/treasure hunt: given total duration, team count, and difficulty, computes a recommended clue count, an easy/medium/hard difficulty mix that ramps harder toward the finish, estimated solving and total time, a suggested hint threshold, and (for 2+ teams) staggered- start guidance to avoid checkpoint bottlenecks. This is a documented planning heuristic, not a guarantee — always test-run your own clues before the real event. Use for "how many clues for a 60 minute hunt with 4 teams", "pacing plan for a hard 90 minute hunt". Args: duration_minutes, num_teams, difficulty.
find_format_for_occasion — Suggests which clue formats and hunt-design choices fit a stated occasion: typical group size and duration, recommended difficulty, whether team or individual format suits it best, recommended clue formats, and occasion-specific tips. Use for "what clue formats work well for a wedding", "how should I run a hunt for a corporate team-building event". Args: occasion.
venue_consideration — Planning considerations, safety notes, permission/permit notes, weather notes, accessibility notes, and recommended clue formats for a named venue type, indoor or outdoor. Use for "what should I consider for an outdoor park hunt", "is a museum a good venue for a scavenger hunt". Args: venue_type.
term_glossary — Definitions of common scavenger/treasure-hunt vocabulary — clue chain, hub-and-spoke, red herring, decoy clue, checkpoint, game master, difficulty curve, meta-puzzle, and more. Use for "what does 'hub-and-spoke' mean", "define red herring in a scavenger hunt". Args: term.
category_list — Every clue-format category with how many formats are in it (Wordplay & Riddles, Visual & Photo, Location & Navigation, Tech-Assisted, Physical & Sensory, Hybrid & Combination). Use for "what categories of clue formats do you cover".
beginner_tips — A ranked shortlist of general tips for planning a first scavenger or treasure hunt — testing clues in advance, backup plans for tech-dependent clues, briefing safety, hint systems, and more. Use for "give me tips for planning my first scavenger hunt". Args: count.
ok: true with data, or ok: false with a structured error (bad_input, not_found, upstream_error). degraded lists optional sources that were unreachable.Retry-After. initialize and tools/list are never counted.agent@connectorbay.com · connectorbay.com/scavenger/support
Effective 25 September 2026. Unify Dynamics LLC ("we", "us"), Menlo Park, California.
What Scavenger is. Scavenger is a connector (an MCP server and REST API) that AI assistants and personal agents call on your behalf for a hand-curated scavenger-hunt & treasure-hunt design reference — clue formats, occasion fit, and a genuine pacing planner. You interact with your assistant; the assistant sends us only the arguments needed for that one lookup.
What we receive. The arguments of each tool call, the technical headers needed to serve the request (an IP address or a client identifier supplied by the assistant, and a Pro API key if you have one), and standard server logs.
Everything is answered from a bundled, hand-curated reference file and nothing is stored. No request is forwarded to any third party — there is no upstream call at all, live or otherwise — and no query is logged in request bodies, recorded, or used to train anything.
What we do not receive or store. We do not receive your conversation with the assistant or your name, and we do not build a profile from your queries: each request is answered independently and nothing carries over between requests. Rate-limit counters (a client identifier and timestamps) are held in memory for at most 24 hours. Hosting-provider access logs, which contain IP addresses and request paths but not request bodies, are retained for up to 30 days for security and abuse prevention.
Sub-processors. None — the entire dataset is bundled with the server and answered locally. Hosting: Vercel (United States regions).
Legal bases and your rights. Our processing is necessary to provide the service you request through your assistant. Because we store no personal data beyond short-lived logs, requests to access, correct or delete personal data are usually satisfied automatically; you can still contact agent@connectorbay.com and we will respond within 30 days. We do not sell or share personal information and do not use your data to train models.
Children. Scavenger is a general-audience service operated by the adult using the assistant.
Changes. We will post changes here with a new effective date.
Effective 25 September 2026. These terms govern use of the Scavenger connector ("the Service") operated by Unify Dynamics LLC ("we", "us").
Email agent@connectorbay.com. We answer within two business days.
https://scavenger.connectorbay.com/mcphttps://scavenger.connectorbay.com/openapi.jsonWhen you report a problem, include the question you asked your agent, roughly when, and which agent you used (for example Claude, ChatGPT or Gemini). Never send us passwords, account numbers or ID numbers. Scavenger never asks for them.